分子结构无法告诉我们的事:基于GNN的药物毒性预测中可解释性差距的分类
What Molecular Structure Cannot Tell Us: A Taxonomy of Explainability Gaps in GNN-Based Drug Toxicity Prediction
AI总结:
本研究引入了一个操作分类法,系统性地分析了图神经网络在药物毒性预测中由于结构信息限制导致的不可解释性差距,并以阿司匹林为例量化了分子结构仅能解释约45%的不良反应。
摘要:
并非所有临床相关的不良反应都能从分子图中结构推断出来——无论模型质量或架构复杂性如何。本研究引入了一个操作分类法,用于描述独立于所用学习算法的结构信息限制,这些限制阻碍了基于结构的毒性预测。图神经网络(GNN)已成为分子毒性预测的自然方法,直接作用于原子连接性,避免了固定长度指纹固有的信息损失。然而,药物已知药理学特征中实际可从分子结构推断的比例仍未被系统探索。以乙酰水杨酸(ASA,阿司匹林)——药理学中表征最全面的药物之一——作为模型化合物进行系统性案例研究。在Tox21基准上训练消息传递神经网络(MPNN),并应用GNNExplainer表征原子级归因。结果表明,分子结构解释了约45%(5/11)的已知ASA不良反应。引入了一个四类差距分类法(GAP-1至GAP-4),区分了原则上不可编码的效应、由非随机缺失(MNAR)机制引起的数据差距、检测面板不匹配和表示误差。通过系统的ChEMBL查询(42个已记录检测,0个可检索生物活性条目)经验量化了MNAR差距。注意力池化实验将表示误差定位到MPNN消息传递层而非聚合步骤。该差距分类法对药物安全信号检测和监管框架(包括良好药物警戒实践(GVP)指南和新方法论(NAMs))具有直接影响。在伴随的DDI消融研究中确认了所识别的结构限制。
英文摘要:
Not all clinically relevant adverse effects are structurally inferable from molecular graphs - regardless of model quality or architectural complexity. This study introduces an operational taxonomy of the structural information limits that prevent structure-based toxicity prediction, independent of the learning algorithm employed. Graph Neural Networks (GNNs) have emerged as a natural approach for molecular toxicity prediction, operating directly on atomic connectivity without the information loss inherent to fixed-length fingerprints. However, the fraction of a drug's known pharmacological profile that is actually inferable from molecular structure remains systematically underexplored. A systematic case study using acetylsalicylic acid (ASA, Aspirin) - one of the most comprehensively characterized drugs in pharmacology - serves as model compound. A Message Passing Neural Network (MPNN) is trained on the Tox21 benchmark and GNNExplainer is applied to characterize atom-level attribution. Results indicate that molecular structure explains approximately 45% (5/11) of known ASA adverse effects. A four-category Gap Taxonomy (GAP-1 through GAP-4) is introduced distinguishing between principally non-encodable effects, data gaps arising from Missing Not At Random (MNAR) mechanisms, assay panel mismatches, and representation errors. The MNAR gap is empirically quantified via a systematic ChEMBL query (42 documented assays, 0 retrievable bioactivity entries). An attention pooling experiment localizes the representation error to the MPNN message passing layers rather than the aggregation step. The Gap Taxonomy has direct implications for drug safety signal detection and regulatory frameworks including Good Pharmacovigilance Practice (GVP) guidelines and New Approach Methodologies (NAMs). Structural limits identified are confirmed in a companion DDI ablation study.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。